Instructions to use baichuan-inc/Baichuan2-13B-Chat-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use baichuan-inc/Baichuan2-13B-Chat-4bits with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="baichuan-inc/Baichuan2-13B-Chat-4bits", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-13B-Chat-4bits", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use baichuan-inc/Baichuan2-13B-Chat-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "baichuan-inc/Baichuan2-13B-Chat-4bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baichuan-inc/Baichuan2-13B-Chat-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/baichuan-inc/Baichuan2-13B-Chat-4bits

SGLang

How to use baichuan-inc/Baichuan2-13B-Chat-4bits with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "baichuan-inc/Baichuan2-13B-Chat-4bits" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baichuan-inc/Baichuan2-13B-Chat-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "baichuan-inc/Baichuan2-13B-Chat-4bits" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baichuan-inc/Baichuan2-13B-Chat-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use baichuan-inc/Baichuan2-13B-Chat-4bits with Docker Model Runner:
```
docker model run hf.co/baichuan-inc/Baichuan2-13B-Chat-4bits
```

s-JoL commited on Sep 6, 2023

Commit

0496919

1 Parent(s): 3c9628b

Update modeling_baichuan.py

Browse files

Files changed (1) hide show

modeling_baichuan.py +1 -0

modeling_baichuan.py CHANGED Viewed

@@ -181,6 +181,7 @@ class BaichuanAttention(torch.nn.Module):
             # )
             with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=True, enable_mem_efficient=True):
                 attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, attn_mask = attention_mask)
         else:
             attn_weights = torch.matmul(
                 query_states, key_states.transpose(2, 3)

             # )
             with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=True, enable_mem_efficient=True):
                 attn_output = F.scaled_dot_product_attention(query_states, key_states, value_states, attn_mask = attention_mask)
+            attn_output = attn_output.transpose(1, 2)
         else:
             attn_weights = torch.matmul(
                 query_states, key_states.transpose(2, 3)